previewOutfitGiven a characterId and a list of item ids from listItems, return the resolved HoloStage.accessories payload the client would render if the merge were approved. Nothing is persisted.
| Name | Required | Description | Default |
|---|---|---|---|
| itemIds | Yes | ||
| characterId | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses non-persistent behavior explicitly ('Nothing is persisted') and describes the return as the resolved payload, indicating a read-only computation. No annotations exist, so this disclosure is essential. It doesn't cover auth/permissions, but for a simple preview tool the key behavioral trait is covered.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence plus a short declarative sentence. No redundancy, front-loaded with the action and outcome.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description explains purpose, source of item ids, output payload, and non-persistence. It lacks explicit guidance on when to use versus requestMerge, but for a low-complexity tool with no output schema, the core information is present.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema shows two required parameters with types. Description adds that item ids come from listItems and characterId likely identifies a body, but doesn't define the exact domain of characterId or the format of itemIds beyond 'list.' With 0% schema description coverage, this partial compensation yields a score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it takes characterId and item ids to return resolved HoloStage.accessories payload, with 'Nothing is persisted' distinguishing it as a dry-run preview. The phrase 'if the merge were approved' differentiates it from requestMerge.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use or exclusions. 'Dry-run' title and 'Nothing is persisted' imply a preview before merge, but the description doesn't compare to requestMerge or listBodies/listItems.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool fulfills a unique role: greet tests payments, listBodies and listItems list different catalogs, negotiate handles agent spending, previewOutfit visualizes combinations, and requestMerge initiates the final action. No two tools overlap in their core purpose.
Most names follow a camelCase verb_noun pattern (listBodies, listItems, previewOutfit, requestMerge), but greet and negotiate are single verbs without a noun object. This is a minor deviation that doesn't create confusion.
Six tools is well-scoped for the server's purpose of browsing, previewing, and merging agent bodies. Each tool contributes a distinct capability without redundancy or bloat.
The core workflow is covered: browse bodies, check items, negotiate, preview, and request merge. Missing operations like checking merge status or cancelling a request are minor gaps that agents can work around, but they are not fatal.